A robust multi-variability model based liver segmentation algorithm for CT-scan and MRI modalities

• Published in: Computerized medical imaging and graphics Vol. 76; p. 101635
• Main Authors: Lebre, Marie-Ange, Vacavant, Antoine, Grand-Brochier, Manuel, Rositi, Hugo, Strand, Robin, Rosier, Hubert, Abergel, Armand, Chabrot, Pascal, Magnin, Benoît
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.09.2019; Elsevier Science Ltd; Elsevier
• Subjects: 3-D; Adequacy; Algorithms; Automatic segmentation; Computed tomography; Computer Science; Image processing; Image segmentation; Liver; Magnetic resonance imaging; Medical Imaging; MRI; NMR; Nuclear magnetic resonance; Organs; Robustness; Shape model; Signal and Image Processing; Variability; CT; Automatic segmentation; MRI; Liver; Variability; Shape model; 3-D; Robustness
• ISSN: 0895-6111; 1879-0771; 1879-0771
• DOI: 10.1016/j.compmedimag.2019.05.003

•The study presents a method of a liver extraction for both modalities: on abdominal computerized tomography (CT) images and also on magnetic resonance imaging (MRI) images.•The method is automatic and based on the shape variability of the liver from a large quantity of CT and MRI images.•A new precise definition to measure the robustness is presented. This measure takes into account the liver variability at different scales.•Evaluation of liver segmentation provided by various CT and MRI images shows that the method achieves an average Dice value of 90.3%. The 3D visualization of the results is presented.•A large comparison with different methods shows the performance on both modalities with this automatic algorithm. Developing methods to segment the liver in medical images, study and analyze it remains a significant challenge. The shape of the liver can vary considerably from one patient to another, and adjacent organs are visualized in medical images with similar intensities, making the boundaries of the liver ambiguous. Consequently, automatic or semi-automatic segmentation of liver is a difficult task. Moreover, scanning systems and magnetic resonance imaging have different settings and parameters. Thus the images obtained differ from one machine to another. In this article, we propose an automatic model-based segmentation that allows building a faithful 3-D representation of the liver, with a mean Dice value equal to 90.3% on CT and MRI datasets. We compare our algorithm with a semi-automatic method and with other approaches according to the state of the art. Our method works with different data sources, we use a large quantity of CT and MRI images from machines in various hospitals and multiple DICOM images available from public challenges. Finally, for evaluation of liver segmentation approaches in state of the art, robustness is not adequacy addressed with a precise definition. Another originality of this article is the introduction of a novel measure of robustness, which takes into account the liver variability at different scales.